Izdelava igre za obogatitev jezikovnih podatkov

diplomsko delo

Matej Fortuna (Author), Bojan Klemenc (Mentor), Iztok Kosem (Co-mentor)

Abstract

Zadnje čase se soočamo s problemom vse večje količine podatkov na področju jezikovnih tehnologij. Ti se zaradi velike količine, večinoma obdelujejo avtomatsko s pomočjo modeliranja naravnega jezika. Pri tem velikokrat pride do napak, kjer pridejo v igro leksikografi, ki pa nimajo vedno dovolj časa, da bi se ukvarjali s takimi problemi. V diplomski nalogi sta predstavljena načrtovanje in razvoj rešitve problema. Rešitev problema je izdelava igre za množičenje podatkov, ki se je v preteklosti izkazala za dobro rešitev. Ta koncept nam pomaga pridobiti pravilne podatke, ki olajšajo delo leksikografom, medtem ko govorce naravnega jezika zabava in pouči o slovenskem jeziku. Igra je izdelana za naprave z operacijskim sistemom Android, ampak je zaradi vsestranskost Unityja hitro prenesljiva na druge medije. Razdeljena je na dva dela in sicer na del za množičenje in del za zadrževanje uporabnikov. Zato bo igra obdržala igralce in pomagala pridobivati podatke.

Keywords

Unity;Django;jezikovna igra;množičenje;visokošolski strokovni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2022
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[M. Fortuna]
UDC:	004.9:81'322.2(043.2)
COBISS:	101071107
Views:	127
Downloads:	10
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Development of a game for language data augmentation
Secondary abstract:	Recently, we have been facing a problem of increasing amounts of data in the field of language technologies. Due to a large amount of data, it is mostly processed automatically with the help of natural language modeling. It seems, however, that there are often mistakes, and that is where lexicographers come into play. But they do not always have enough time to deal with such problems. The bachelor's thesis presents the planning and development of a solution to the aforementioned problem. The solution is to make a game using crowdsourcing, which has been proven to work well in the past. This concept helps us to obtain the correct data that facilitates the work of lexicographers while entertaining and teaching natural language speakers about the Slovenian language. The game is made for devices using the Android operating system. Due to the versatility of Unity, however, it can be quickly transferred to other platforms. It is divided into two parts: the crowdsourcing part and the user retention part. Because of this, the game will retain players and help us retrieve data.
Secondary keywords:	Unity;Django;Word game;crowdsourcing;computer science;diploma;Obdelava naravnega jezika (računalništvo);Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000470
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	28 str.
ID:	14759917